{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MVWCK7Z5JK7BOADR7GOEJPJ6G4","short_pith_number":"pith:MVWCK7Z5","canonical_record":{"source":{"id":"2205.14327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-28T04:05:20Z","cross_cats_sorted":[],"title_canon_sha256":"d7526b7450e35ecb86c1ebede14a99f79f70a0d46b51c07672a8846762f327a1","abstract_canon_sha256":"7ef80733cd13bbee6b9d6b9c4c82c138700865426042dd21477b87b0d24ee74f"},"schema_version":"1.0"},"canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","source":{"kind":"arxiv","id":"2205.14327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14327","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14327v2","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14327","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"MVWCK7Z5JK7B","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"MVWCK7Z5JK7BOADR","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"MVWCK7Z5","created_at":"2026-07-05T05:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MVWCK7Z5JK7BOADR7GOEJPJ6G4","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-28T04:05:20Z","cross_cats_sorted":[],"title_canon_sha256":"d7526b7450e35ecb86c1ebede14a99f79f70a0d46b51c07672a8846762f327a1","abstract_canon_sha256":"7ef80733cd13bbee6b9d6b9c4c82c138700865426042dd21477b87b0d24ee74f"},"schema_version":"1.0"},"canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:37.625487Z","signature_b64":"Adumf4YYHXKCcwn8NODSYMnHSYqBE9I/WHD83CXvrJKCaIu/k2IMWf63zmbJVIe1RUfkzQsWd0lxL08BduvSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","last_reissued_at":"2026-07-05T05:03:37.625027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:37.625027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14327","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hs6+vsW+9kuwoTZE1naWyXOl5CVTxwnsH3E2nwVNmzd/LSFwOkIGCvcon40eTDxQyCyxb4E40KqVqwJ4qN8VCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:52:50.479365Z"},"content_sha256":"9018047fcfec12bc67bdca4dd496a59a01e8925f207153ae7d7446c5e1f7d326","schema_version":"1.0","event_id":"sha256:9018047fcfec12bc67bdca4dd496a59a01e8925f207153ae7d7446c5e1f7d326"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MVWCK7Z5JK7BOADR7GOEJPJ6G4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kaixin Wang, Kfir Levy, Navdeep Kumar, Shie Mannor","submitted_at":"2022-05-28T04:05:20Z","abstract_excerpt":"Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for some \\texttt{sa}-rectangular robust MDPs exist, using its equivalence with reward regularized MDPs, generalizable to online settings. In comparison to \\texttt{sa}-rectangular robust MDPs, \\texttt{s}-rectangular robust MDPs are less restrictive but much more difficult to deal with. Interestingly, recent works have established the equivalence between \\texttt{s}-rectangular robust MDPs and policy regularized MDPs. But "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14327","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.14327/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nIcCmR8S72ct3pX+QjweTgXLUCtSoG8+urgFZs4rnkO5mIg49TvQYqHHUNnw8kkqVxz/yeGh18FiggQc6TrtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:52:50.480296Z"},"content_sha256":"fd15235d634c8679e9cd1d7d92083eed103edca8b3721c0a691d1daaf99df3b8","schema_version":"1.0","event_id":"sha256:fd15235d634c8679e9cd1d7d92083eed103edca8b3721c0a691d1daaf99df3b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/bundle.json","state_url":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T05:52:50Z","links":{"resolver":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4","bundle":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/bundle.json","state":"https://pith.science/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVWCK7Z5JK7BOADR7GOEJPJ6G4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MVWCK7Z5JK7BOADR7GOEJPJ6G4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7ef80733cd13bbee6b9d6b9c4c82c138700865426042dd21477b87b0d24ee74f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-28T04:05:20Z","title_canon_sha256":"d7526b7450e35ecb86c1ebede14a99f79f70a0d46b51c07672a8846762f327a1"},"schema_version":"1.0","source":{"id":"2205.14327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14327","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14327v2","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14327","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"MVWCK7Z5JK7B","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"MVWCK7Z5JK7BOADR","created_at":"2026-07-05T05:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"MVWCK7Z5","created_at":"2026-07-05T05:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:fd15235d634c8679e9cd1d7d92083eed103edca8b3721c0a691d1daaf99df3b8","target":"graph","created_at":"2026-07-05T05:03:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.14327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for some \\texttt{sa}-rectangular robust MDPs exist, using its equivalence with reward regularized MDPs, generalizable to online settings. In comparison to \\texttt{sa}-rectangular robust MDPs, \\texttt{s}-rectangular robust MDPs are less restrictive but much more difficult to deal with. Interestingly, recent works have established the equivalence between \\texttt{s}-rectangular robust MDPs and policy regularized MDPs. But ","authors_text":"Kaixin Wang, Kfir Levy, Navdeep Kumar, Shie Mannor","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-28T04:05:20Z","title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14327","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9018047fcfec12bc67bdca4dd496a59a01e8925f207153ae7d7446c5e1f7d326","target":"record","created_at":"2026-07-05T05:03:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7ef80733cd13bbee6b9d6b9c4c82c138700865426042dd21477b87b0d24ee74f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-28T04:05:20Z","title_canon_sha256":"d7526b7450e35ecb86c1ebede14a99f79f70a0d46b51c07672a8846762f327a1"},"schema_version":"1.0","source":{"id":"2205.14327","kind":"arxiv","version":2}},"canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"656c257f3d4abe170071f99c44bd3e3703af78dc4e6a914ff63e7af9c6315868","first_computed_at":"2026-07-05T05:03:37.625027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:37.625027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Adumf4YYHXKCcwn8NODSYMnHSYqBE9I/WHD83CXvrJKCaIu/k2IMWf63zmbJVIe1RUfkzQsWd0lxL08BduvSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:37.625487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9018047fcfec12bc67bdca4dd496a59a01e8925f207153ae7d7446c5e1f7d326","sha256:fd15235d634c8679e9cd1d7d92083eed103edca8b3721c0a691d1daaf99df3b8"],"state_sha256":"ce16618541ae988c5b22e9e7dac953f5d4cb1e575692aa31fb8d1fe9a1d94f7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YbLUc6BzlesFHKz3NVwAfXJw2/9MWdPtAFN0ChsLQ9Lpra8VXSa4qeE2UkqYMcgP7IIXhVebRkD37o/zreNPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:52:50.486912Z","bundle_sha256":"a74ed2a955e753b3fe432d74522bc4f22fb8187442ed7d80f2ade89a46f3193d"}}